CAMS: RESIDUAL CAPABILITY ALLOCATION FOR CONTINUED TOOL-USE SFT

Data selection for tool-use supervised fine-tuning commonly ranks records by global quality, relevance, or estimated utility. Staged adaptation raises a more specific question: once a model has completed initial adaptation, which remaining training records should form the next batch for continued training under a fixed budget? We define this setting as marginal continuation selection and introduce Capability-Aware Marginal Selection (CAMS). CAMS matches what the current model still needs with what supervision each candidate record provides. A frozen train-side probe supplies capability accuracies $C_k$, yielding $D_k=1-C_k$ as a residual-headroom proxy; gold tool calls and TRAIN statistics supply observable supervision demands $V_k$. CAMS ranks candidates by $S(\tau \mid \theta )={\sum }_k{D}_k(\theta )V_k(\tau )$ and admits intact records under the continuation budget. The current instantiation uses two auditable demand axes: multi-binding structure and API exposure scarcity. We evaluate on the frozen API-Bank train-side confirmation set (FCS): 256 converted API-call records disjoint from training, the capability probe, and selector-construction records. On Qwen3-8B under the frozen API-Bank continuation protocol, CAMS achieves 35.29% exact API-call correctness on FCS, the highest mean among five baselines fixed before confirmation evaluation. It exceeds the strongest pre-frozen baseline by 1.83 percentage points and same-state Random by 2.65 points, with positive CAMS–Random differences in all three training states. Post-hoc descriptive CAMS–Random differences are 10.0 points on multi-argument calls and 13.43 points on rare-API calls. CAMS frames continued tool-use SFT as model-state-aware residual capability allocation: matching current needs to observable supervision in the remaining data, rather than repeating a static global ranking.